{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WEU4LBBHD2C2DSPUZSYM4MMICY","short_pith_number":"pith:WEU4LBBH","schema_version":"1.0","canonical_sha256":"b129c584271e85a1c9f4ccb0ce3188161c63782e79b97de8c2c0b2f263332528","source":{"kind":"arxiv","id":"2411.13083","version":2},"attestation_state":"computed","paper":{"title":"Omnipredicting Single-Index Models with Multi-Index Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chutong Yang, Kevin Tian, Lunjia Hu","submitted_at":"2024-11-20T07:20:49Z","abstract_excerpt":"Recent work on supervised learning [GKR+22] defined the notion of omnipredictors, i.e., predictor functions $p$ over features that are simultaneously competitive for minimizing a family of loss functions $\\mathcal{L}$ against a comparator class $\\mathcal{C}$. Omniprediction requires approximating the Bayes-optimal predictor beyond the loss minimization paradigm, and has generated significant interest in the learning theory community. However, even for basic settings such as agnostically learning single-index models (SIMs), existing omnipredictor constructions require impractically-large sample"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.13083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T07:20:49Z","cross_cats_sorted":["cs.DS","math.OC","stat.ML"],"title_canon_sha256":"a1a355119349d4c37994d7a64d23bac1d74f5b1bb6edc89dac7b13c1f26c3b47","abstract_canon_sha256":"44efd9019bebb54468d6368f326730e0f3e83824205314733eb36544c815f1f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:48.160132Z","signature_b64":"l5XTVlyuo8xliiOfwk7HTcO9tbWCp5GBpn7sipiJh/aMDUDJ0AeMx2lxb2cAW168n6IAftgsiYUxOAa6P1nKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b129c584271e85a1c9f4ccb0ce3188161c63782e79b97de8c2c0b2f263332528","last_reissued_at":"2026-07-05T10:03:48.159598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:48.159598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Omnipredicting Single-Index Models with Multi-Index Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chutong Yang, Kevin Tian, Lunjia Hu","submitted_at":"2024-11-20T07:20:49Z","abstract_excerpt":"Recent work on supervised learning [GKR+22] defined the notion of omnipredictors, i.e., predictor functions $p$ over features that are simultaneously competitive for minimizing a family of loss functions $\\mathcal{L}$ against a comparator class $\\mathcal{C}$. Omniprediction requires approximating the Bayes-optimal predictor beyond the loss minimization paradigm, and has generated significant interest in the learning theory community. However, even for basic settings such as agnostically learning single-index models (SIMs), existing omnipredictor constructions require impractically-large sample"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13083","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.13083/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.13083","created_at":"2026-07-05T10:03:48.159661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13083v2","created_at":"2026-07-05T10:03:48.159661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13083","created_at":"2026-07-05T10:03:48.159661+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEU4LBBHD2C2","created_at":"2026-07-05T10:03:48.159661+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEU4LBBHD2C2DSPU","created_at":"2026-07-05T10:03:48.159661+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEU4LBBH","created_at":"2026-07-05T10:03:48.159661+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20885","citing_title":"Improved Bounds for Swap Multicalibration and Swap Omniprediction","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WEU4LBBHD2C2DSPUZSYM4MMICY","json":"https://pith.science/pith/WEU4LBBHD2C2DSPUZSYM4MMICY.json","graph_json":"https://pith.science/api/pith-number/WEU4LBBHD2C2DSPUZSYM4MMICY/graph.json","events_json":"https://pith.science/api/pith-number/WEU4LBBHD2C2DSPUZSYM4MMICY/events.json","paper":"https://pith.science/paper/WEU4LBBH"},"agent_actions":{"view_html":"https://pith.science/pith/WEU4LBBHD2C2DSPUZSYM4MMICY","download_json":"https://pith.science/pith/WEU4LBBHD2C2DSPUZSYM4MMICY.json","view_paper":"https://pith.science/paper/WEU4LBBH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13083&json=true","fetch_graph":"https://pith.science/api/pith-number/WEU4LBBHD2C2DSPUZSYM4MMICY/graph.json","fetch_events":"https://pith.science/api/pith-number/WEU4LBBHD2C2DSPUZSYM4MMICY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEU4LBBHD2C2DSPUZSYM4MMICY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEU4LBBHD2C2DSPUZSYM4MMICY/action/storage_attestation","attest_author":"https://pith.science/pith/WEU4LBBHD2C2DSPUZSYM4MMICY/action/author_attestation","sign_citation":"https://pith.science/pith/WEU4LBBHD2C2DSPUZSYM4MMICY/action/citation_signature","submit_replication":"https://pith.science/pith/WEU4LBBHD2C2DSPUZSYM4MMICY/action/replication_record"}},"created_at":"2026-07-05T10:03:48.159661+00:00","updated_at":"2026-07-05T10:03:48.159661+00:00"}